Thanks for your nice paper and implementations,
Currently I try to use sine activation function on some implicit image restoration functions,
In here I have little question about w0 implementation
Multiply of w0
In paper w0=30 in initial layer is represented with y = sin(w0*wx+b) in last sentence of paragraph 3.2
But in Implementation,
MetaSequential(BatchLinear(in_features, hidden_features), nl))BatchLinear(in_features, hidden_features) for (wx+b)
and nl make y = sin(w0*(wx+b))
I check that performance goes well in your distributed experiments,
but is there any problems to use w0 multiply on bias?
It just make smaller bias only?
Initialize of w
In paper paragraph 3.2 and supplement 1.5
Initialize of w should goes with
-sqrt(6/n), sqrt(6/n) in paragraph 3.2
or
-sqrt(6/n)/w0, sqrt(6/n)/w0when use with w0 value,
but In distributed source,
first layer use w0=30 but it's initialization of w is -1/n , 1/n
where can I find the reason for this first layer initialization?
Hello @vsitzmann ,
Thanks for your nice paper and implementations, Currently I try to use sine activation function on some implicit image restoration functions,
In here I have little question about w0 implementation
In paper w0=30 in initial layer is represented with y = sin(w0*wx+b) in last sentence of paragraph 3.2 But in Implementation,
MetaSequential(BatchLinear(in_features, hidden_features), nl))
BatchLinear(in_features, hidden_features)
for (wx+b) andnl
make y = sin(w0*(wx+b))I check that performance goes well in your distributed experiments, but is there any problems to use w0 multiply on bias? It just make smaller bias only?
In paper paragraph 3.2 and supplement 1.5
Initialize of w should goes with
-sqrt(6/n), sqrt(6/n)
in paragraph 3.2 or-sqrt(6/n)/w0, sqrt(6/n)/w0
when use with w0 value,but In distributed source,
first layer use w0=30 but it's initialization of w is
-1/n , 1/n
where can I find the reason for this first layer initialization?